Brian Kade Betterton

Recovering vulnerability detection on realistically-distributed code

This thesis rebuilds Real-Vul through a controlled Code Property Graph pipeline, measure and remove a 37% content leak intrinsic to whole-codebase sampling, and train a relational graph neural network with a disciplined class-imbalance recipe: focal loss, class-aware undersampling, and fine-tuning of a GraphCodeBERT no...